Papers with Code 아카이브
Adversarial Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 3
- 보존된 평가 기록
- 9
An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.
Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/imrahulr/adversarial_robustness_pytorch
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/inspire-group/advml-traffic-sign
https://github.com/itsayushthada/Text-To-Image
https://github.com/jacobgil/pytorch-grad-cam
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
https://github.com/jailbreakbench/jailbreakbench
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/jaryp/pixleattack
Scratch that! An Evolution-based Adversarial Attack against Neural Networks
https://github.com/jay-z007/Text-to-Image-Synthesis
https://github.com/jdrego/EEE511ANC-Text2ImageGAN
https://github.com/jeongjin0/detector-cleanse
https://github.com/jeromerony/adversarial-library
https://github.com/jfc43/pixel-discretization
https://github.com/jfc43/robust-attribution-regularization
https://github.com/jinyuan-jia/badencoder
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
https://github.com/johnsonkee/graduate_design
https://github.com/jokeryan/post_training
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/jsrdcht/SSL-Backdoor
https://github.com/jzhang538/corruptencoder
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
https://github.com/keonlee9420/WaveGrad2
https://github.com/khieu/cifar10_challenge
https://github.com/kkew3/pytorch-cw2
https://github.com/lancopku/rap
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
https://github.com/lemonadec/Relevance-between-Accuracy-under-Black-box-Attack-and-the-Similarity-between-Networks
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/linweiii/backdoordm
https://github.com/liu00222/StolenEncoder
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
https://github.com/locuslab/breaking-poisoned-classifier
https://github.com/locuslab/fast_adversarial
https://github.com/locuslab/robust_overfitting
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/locuslab/smoothing
https://github.com/loes5307/vocaladversary2022
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/lovelyqian/wave-SAN-CDFSL
StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning
https://github.com/luizgh/adversarial_signatures
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/makezur/vib_pytorch
https://github.com/maremun/GenAttackMCS2018
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
https://github.com/matanbt/attack-tabular
https://github.com/matheushent/score-cam
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.